SeedVR2

ComfyUI-SeedVR2_VideoUpscaler

View Code

Official release of SeedVR2 for ComfyUI that enables high-quality video and image upscaling.

Can run as Multi-GPU standalone CLI too, see 🖥️ Run as Standalone section.

SeedVR2 v2.5 Deep Dive Tutorial

Usage Example

Usage Example

📋 Quick Access

• 🆙 Future Releases
• 🚀 Updates
• 🎯 Features
• 🔧 Requirements
• 📦 Installation
• 📖 Usage
• 🖥️ Run as Standalone
• ⚠️ Limitations
• 🤝 Contributing
• 🙏 Credits
• 📜 License

🆙 Future Releases

We're actively working on improvements and new features. To stay informed:

• 📌 Track Active Development: Visit Issues to see active development, report bugs, and request new features
• 💬 Join the Community: Learn from others, share your workflows, and get help in the Discussions
• 🔮 Next Model Survey: We're looking for community input on the next open-source super-powerful generic restoration model. Share your suggestions in Issue #164

🚀 Updates

2025.11.09 - Version 2.5.5

• 💾 Memory: Fixed RAM leak for long videos - On-demand reconstruction with lightweight batch indices instead of storing full transformed videos, fixed release_tensor_memory to handle CPU/CUDA/MPS consistently, and refactored batch processing helpers

2025.11.08 - Version 2.5.4

• 🎨 Fix: AdaIN color correction - Replace .view() with .reshape() to handle non-contiguous tensors after spatial padding, resolving "view size is not compatible with input tensor's size and stride" error
• 🔴 Fix: AMD ROCm compatibility - Add cuDNN availability check in Conv3d workaround to prevent "ATen not compiled with cuDNN support" error on ROCm systems (AMD GPUs on Windows/Linux)

2025.11.08 - Version 2.5.3

• 🍎 Fix: Apple Silicon MPS device handling - Corrected MPS device enumeration to use "mps" instead of "mps:0", resolving invalid device errors on M-series Macs
• 🪟 Fix: torch.mps AttributeError on Windows - Add defensive checks for torch.mps.is_available() to handle PyTorch versions where the method doesn't exist on non-Mac platforms

2025.11.07 - Version 2.5.0 🎉

⚠️ BREAKING CHANGE: This is a major update requiring workflow recreation. All nodes and CLI parameters have been redesigned for better usability and consistency. Watch the latest video from AInVFX for a deep dive and check out the usage section.

📦 Official Release: Now available on main branch with ComfyUI Manager support for easy installation and automatic version tracking. Updated dependencies and local imports prevent conflicts with other ComfyUI custom nodes.

🎨 ComfyUI Improvements

• Four-Node Modular Architecture: Split into dedicated nodes for DiT model, VAE model, torch.compile settings, and main upscaler for granular control
• Global Model Cache: Models now shared across multiple upscaler instances with automatic config updates - no more redundant loading
• ComfyUI V3 Migration: Full compatibility with ComfyUI V3 stateless node design
• RGBA Support: Native alpha channel processing with edge-guided upscaling for clean transparency
• Improved Memory Management: Streaming architecture prevents VRAM spikes regardless of video length
• Flexible Resolution Support: Upscale to any resolution divisible by 2 with lossless padding approach (replaced restrictive cropping)
• Enhanced Parameters: Added uniform_batch_size, temporal_overlap, prepend_frames, and max_resolution for better control

🖥️ CLI Enhancements

• Batch Directory Processing: Process entire folders of videos/images with model caching for efficiency
• Single Image Support: Direct image upscaling without video conversion
• Smart Output Detection: Auto-detects output format (MP4/PNG) based on input type
• Enhanced Multi-GPU: Improved workload distribution with temporal overlap blending
• Unified Parameters: CLI and ComfyUI now use identical parameter names for consistency
• Better UX: Auto-display help, validation improvements, progress tracking, and cleaner output

⚡ Performance & Optimization

• torch.compile Support: 20-40% DiT speedup and 15-25% VAE speedup with full graph compilation
• Optimized BlockSwap: Adaptive memory clearing (5% threshold), separate I/O component handling, reduced overhead
• Enhanced VAE Tiling: Tensor offload support for accumulation buffers, separate encode/decode configuration
• Native Dtype Pipeline: Eliminated unnecessary conversions, maintains bfloat16 precision throughout for speed and quality
• Optimized Tensor Operations: Replaced einops rearrange with native PyTorch ops for 2-5x faster transforms

🎯 Quality Improvements

• LAB Color Correction: New perceptual color transfer method with superior color accuracy (now default)
• Additional Color Methods: HSV saturation matching, wavelet adaptive, and hybrid approaches
• Deterministic Generation: Seed-based reproducibility with phase-specific seeding strategy
• Better Temporal Consistency: Hann window blending for smooth transitions between batches

💾 Memory Management

• Smarter Offloading: Independent device configuration for DiT, VAE, and tensors (CPU/GPU/none)
• Four-Phase Pipeline: Completes each phase (encode→upscale→decode→postprocess) for all batches before moving to next, minimizing model swaps
• Better Cleanup: Phase-specific resource management with proper tensor memory release
• Peak VRAM Tracking: Per-phase memory monitoring with summary display

🔧 Technical Improvements

• GGUF Quantization Support: Added full GGUF support for 4-bit/8-bit inference on low-VRAM systems
• Improved GGUF Handling: Fixed VRAM leaks, torch.compile compatibility, non-persistent buffers
• Apple Silicon Support: Full MPS (Metal Performance Shaders) support for Apple Silicon Macs
• AMD ROCm Compatibility: Conditional FSDP imports for PyTorch ROCm 7+ support
• Conv3d Memory Workaround: Fixes PyTorch 2.9+ cuDNN memory bug (3x usage reduction)
• Flash Attention Optional: Graceful fallback to SDPA when flash-attn unavailable

📚 Code Quality

• Modular Architecture: Split monolithic files into focused modules (generation_phases, model_configuration, etc.)
• Comprehensive Documentation: Extensive docstrings with type hints across all modules
• Better Error Handling: Early validation, clear error messages, installation instructions
• Consistent Logging: Unified indentation, better categorization, concise messages

2025.08.07

• 🎯 Unified Debug System: New structured logging with categories, timers, and memory tracking. enable_debug now available on main node
• ⚡ Smart FP8 Optimization: FP8 models now keep native FP8 storage, converting to BFloat16 only for arithmetic - faster and more memory efficient than FP16
• 📦 Model Registry: Multi-repo support (numz/ & AInVFX/), auto-discovery of user models, added mixed FP8 variants to fix 7B artifacts
• 💾 Model Caching: cache_model moved to main node, fixed memory leaks with proper RoPE/wrapper cleanup
• 🧹 Code Cleanup: New modular structure (constants.py, model_registry.py, debug.py), removed legacy code
• 🚀 Performance: Better memory management with torch.cuda.ipc_collect(), improved RoPE handling

2025.07.17

• 🛠️ Add 7B sharp Models: add 2 new 7B models with sharpen output

2025.07.11

• 🎬 Complete tutorial released: Adrien from AInVFX created an in-depth ComfyUI SeedVR2 guide covering everything from basic setup to advanced BlockSwap techniques for running on consumer GPUs. Perfect for understanding memory optimization and upscaling of image sequences with alpha channel! Watch the tutorial

2025.09.07

• 🛠️ Blockswap Integration: Big thanks to Adrien Toupet from AInVFX for this :), useful for low VRAM users (see usage section)

2025.07.03

• 🛠️ Can run as standalone mode with Multi GPU see 🖥️ Run as Standalone

2025.06.30

• 🚀 Speed Up the process and less VRAM used
• 🛠️ Fixed memory leak on 3B models
• ❌ Can now interrupt process if needed
• ✅ Refactored the code for better sharing with the community, feel free to propose pull requests
• 🛠️ Removed flash attention dependency (thanks to luke2642 !!)

2025.06.24

• 🚀 Speed up the process until x4

2025.06.22

• 💪 FP8 compatibility !
• 🚀 Speed Up all Process
• 🚀 less VRAM consumption (Stay high, batch_size=1 for RTX4090 max, I'm trying to fix that)
• 🛠️ Better benchmark coming soon

2025.06.20

• 🛠️ Initial push

🎯 Features

Core Capabilities

• High-Quality Diffusion-Based Upscaling: One-step diffusion model for video and image enhancement
• Temporal Consistency: Maintains coherence across video frames with configurable batch processing
• Multi-Format Support: Handles RGB and RGBA (alpha channel) for both videos and images
• Any Video Length: Suitable for any video length

Model Support

• Multiple Model Variants: 3B and 7B parameter models with different precision options
• FP16, FP8, and GGUF Quantization: Choose between full precision (FP16), mixed precision (FP8), or heavily quantized GGUF models for different VRAM requirements
• Automatic Model Downloads: Models are automatically downloaded from HuggingFace on first use

Memory Optimization

• BlockSwap Technology: Dynamically swap transformer blocks between GPU and CPU memory to run large models on limited VRAM
• VAE Tiling: Process large resolutions with tiled encoding/decoding to reduce VRAM usage
• Intelligent Offloading: Offload models and intermediate tensors to CPU or secondary GPUs between processing phases
• GGUF Quantization Support: Run models with 4-bit or 8-bit quantization for extreme VRAM savings

Performance Features

• torch.compile Integration: Optional 20-40% DiT speedup and 15-25% VAE speedup with PyTorch 2.0+ compilation
• Multi-GPU CLI: Distribute workload across multiple GPUs with automatic temporal overlap blending
• Model Caching: Keep models loaded in memory for faster batch processing
• Flexible Attention Backends: Choose between PyTorch SDPA (stable, always available) or Flash Attention 2 (faster on supported hardware)

Quality Control

• Advanced Color Correction: Five methods including LAB (recommended for highest fidelity), wavelet, wavelet adaptive, HSV, and AdaIN
• Noise Injection Controls: Fine-tune input and latent noise scales for artifact reduction at high resolutions
• Configurable Resolution Limits: Set target and maximum resolutions with automatic aspect ratio preservation

Workflow Features

• ComfyUI Integration: Four dedicated nodes for complete control over the upscaling pipeline
• Standalone CLI: Command-line interface for batch processing and automation -...